Search

This report documents the program and the findings of Dagstuhl Seminar 23431 "Network Attack Detection and Defense - AI-Powered Threats and Responses". With the emergence of artificial intelligence (AI), attack detection and defense are taking on a new level of quality. Artificial intelligence will promote further automation of attacks. There are already examples of this, such as the Deep Locker malware. It is expected that we will soon face a situation in which malware and attacks will become more and more automated, intelligent, and AI-powered. Consequently, today’s threat response systems will become more and more inadequate, especially when they rely on manual intervention of security experts and analysts. The main objective of the seminar was to assess the state of the art and potentials that AI advances create for both attackers and defenders. The seminar continued the series of Dagstuhl events "Network Attack Detection and Defense" held in 2008, 2012, 2014, and 2016. The objectives of the seminar were threefold, namely (1) to investigate various scenarios of AI-based malware and attacks, (2) to debate trust in AI and modeling of threats against AI, and (3) to propose methods and strategies for AI-powered network defenses. At the seminar, which brought together participants from academia and industry, we stated that recent advances in artificial intelligence have opened up new possibilities for each of these directions. In general, more and more researchers in networking and security look at AI-based methods which made this a timely event to assess and categorize the state of the art as well as work towards a roadmap for future research. The outcome of the discussions and the proposed research directions are presented in this report.

Machine learning techniques, especially deep neural networks inspired by mathematical models of human intelligence, have reached an unprecedented success on a variety of data analysis tasks. The reliance of critical modern technologies on machine learning, however, raises concerns on their security, especially since powerful attacks against mainstream learning algorithms have been demonstrated since the early 2010s. Despite a substantial body of related research, no comprehensive theory and design methodology is currently known for the security of machine learning. The proposed seminar aims at identifying potential research directions that could lead to building the scientific foundation for the security of machine learning. By bringing together researchers from machine learning and information security communities, the seminar is expected to generate new ideas for security assessment and design in the field of machine learning.